diff --git a/docker/cuda_simple/Dockerfile b/docker/cuda_simple/Dockerfile
index a9e51cdc1..75f47fea0 100644
--- a/docker/cuda_simple/Dockerfile
+++ b/docker/cuda_simple/Dockerfile
@@ -11,7 +11,7 @@ RUN apt-get update && apt-get upgrade -y \
     libclblast-dev libopenblas-dev \
     && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
 
-COPY . .
+# COPY . .
 
 # setting build related env vars
 ENV CUDA_DOCKER_ARCH=all
@@ -20,8 +20,13 @@ ENV LLAMA_CUBLAS=1
 # Install depencencies
 RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings starlette-context
 
-# Install llama-cpp-python (build with cuda)
-RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
+RUN apt install -y git && git clone https://github.com/billcai/llama-cpp-python
+RUN cd llama-cpp-python && \
+    git submodule update --init --recursive && \
+    cd vendor/llama.cpp/ && \
+    make LLAMA_CUBLAS=1 -j8 && \
+    cd ../../ && \
+    CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install . --no-cache-dir
 
 # Run the server
-CMD python3 -m llama_cpp.server
+ENTRYPOINT python3 -m llama_cpp.server